Reaction
NXDirection's data labels are claimed to reduce attack success in two tests
A post says NXDirection labels content as data, with attack success dropping from 38.1% to 0.1% in one test.
TLDR
A post praises NXDirection's approach to separating data from instructions for AI agents. It reports attack success falling from 38.1% to 0.1% in one standard test and from 28.4% to 3.7% in a more complex test. The author cautions that the approach does not solve agent security on its own.
Combined views
—
1 Source, first seen ago
